Control methods for operational robots and operational robots

Abstract

This application discloses a control method for a construction robot and the construction robot itself, belonging to the field of construction technology. The method includes: acquiring an initial point cloud of a target construction space collected by a point cloud acquisition device; identifying concave corner points of each wall surface in the target construction space based on the initial point cloud; acquiring the concave corner distance corresponding to each concave corner point, wherein the concave corner distance is the distance between the concave corner point and the construction robot; determining the distance difference between the concave corner distances corresponding to two concave corner points located on at least one side; and controlling the movement of the construction robot based on the distance difference. This application can improve the operating accuracy of the construction robot.

Description

Technical Field

[0001] This application relates to the field of robot control technology, specifically to a control method for a robot and a robot for operation. Background Technology

[0002] Currently, robots are widely used in operations such as goods transportation and environmental cleaning to perform corresponding tasks. During task execution, it is typically necessary to control the robot to move to the target work location or along a target path to complete the task. However, existing control methods for robot movement suffer from low operational accuracy. Summary of the Invention

[0003] The purpose of this application is to provide a control method and a working robot for a work robot, in order to solve the problem of low operating accuracy of existing work robots.

[0004] To achieve the above objectives, a first aspect of this application provides a control method for a work robot, the work robot including a point cloud acquisition device, the work robot being located within a target construction space, the control method comprising:

[0005] Acquire the initial point cloud of the target construction space collected by the point cloud acquisition device;

[0006] Based on the initial point cloud, identify the concave corner points of each wall surface in the target construction space;

[0007] Obtain the concave corner distance corresponding to each concave corner point. The concave corner distance corresponding to each concave corner point is the distance between that concave corner point and the working robot.

[0008] Determine the distance difference between the concave corner points corresponding to two concave corner points located on at least one side;

[0009] The robot's movement is controlled based on the distance difference.

[0010] In this embodiment of the application, identifying concave corner points of each wall surface in the target construction space based on an initial point cloud includes: obtaining the first direction coordinate value of each point cloud data in the initial point cloud in a first direction; obtaining the point cloud identifier corresponding to each point cloud data; determining adjacent point cloud data in the initial point cloud based on the point cloud identifier corresponding to each point cloud data; determining the coordinate value difference between the first direction coordinate values ​​corresponding to adjacent point cloud data; and determining the concave corner point based on the coordinate value difference, wherein the concave corner point is the point corresponding to the point cloud data whose point cloud identifier is the target point cloud identifier among the adjacent point cloud data whose corresponding coordinate value difference is greater than the preset coordinate value difference.

[0011] In this embodiment of the application, obtaining the point cloud identifier corresponding to each point cloud data includes: clustering the point cloud data in the initial point cloud according to the first direction coordinate value to obtain multiple point cloud clusters; determining the average value of the first direction coordinate value corresponding to the point cloud data in each point cloud cluster; merging and clustering the multiple point cloud clusters according to the average value of the first direction coordinate value to obtain the wall point cloud corresponding to each wall; and obtaining the point cloud identifier corresponding to each point cloud data in each wall point cloud.

[0012] In this embodiment, multiple point cloud clusters each have a corresponding cluster identifier, which is determined based on the number of point cloud data in the cluster. Multiple point cloud clusters are merged and clustered according to the average value of the first direction coordinates to obtain wall point clouds corresponding to each wall surface. This includes: determining adjacent point cloud clusters among the multiple point cloud clusters based on the cluster identifier; determining a first difference in the average value of the first direction coordinates corresponding to adjacent point cloud clusters; and merging and clustering the multiple point cloud clusters according to the first difference to obtain wall point clouds, where each wall point cloud is obtained by merging and clustering adjacent point cloud clusters whose first difference is less than a preset average difference.

[0013] In this embodiment of the application, the work robot also includes multiple distance detection devices, and the control method further includes: acquiring multiple target distance parameters based on the multiple distance detection devices; and adjusting the position and / or posture of the work robot according to the multiple target distance parameters.

[0014] In this embodiment, multiple distance detection devices are respectively disposed on each side of the work robot. The robot's posture is adjusted based on multiple target distance parameters, including: determining a second difference between two adjacent target distance parameters, wherein the two adjacent target distance parameters are detected by distance detection devices disposed on the same side; if the second difference is greater than a preset target distance parameter difference, controlling the work robot to rotate clockwise until the second difference is less than the preset target distance parameter difference error; if the second difference is less than the preset target distance parameter difference, controlling the work robot to rotate counterclockwise until the second difference is less than the preset target distance parameter difference error.

[0015] In this embodiment, multiple distance detection devices are respectively disposed on each side of the work robot. The position of the work robot is adjusted according to multiple target distance parameters, including: acquiring a first distance parameter detected by a distance detection device disposed on a first side and a second distance parameter detected by a distance detection device disposed on a second side, wherein the first side and the second side are oppositely disposed and parallel to each other on the work robot, and the multiple target distance parameters include the first distance parameter and the second distance parameter; when the first distance parameter is greater than the second distance parameter, controlling the work robot to move towards the side where the distance detection device corresponding to the first distance parameter is located.

[0016] In this embodiment of the application, obtaining multiple target distance parameters based on multiple distance detection devices includes: obtaining multiple initial distance parameters detected by multiple distance detection devices; in the case that there is an out-of-range distance parameter among the multiple initial distance parameters, determining the target side where the distance detection device corresponding to the out-of-range distance parameter is located, wherein the out-of-range distance parameter is an initial distance parameter that is greater than a preset distance parameter threshold; removing the initial distance parameters detected by the distance detection devices on the target side from the multiple initial distance parameters to obtain multiple target distance parameters.

[0017] In this embodiment of the application, the control method further includes: obtaining the vertical distance between the spraying robot and each wall surface; determining whether any vertical distance is less than a preset anti-collision distance; and controlling the robot to stop moving if any vertical distance is less than the preset anti-collision distance.

[0018] A second aspect of this application provides a processor configured to execute the above-described control method for a work robot.

[0019] A third aspect of this application provides a work robot, including: a robot body; a point cloud acquisition device; and a processor.

[0020] The aforementioned technical solution acquires an initial point cloud of the target construction space from a point cloud acquisition device. Based on this initial point cloud, it identifies the concave corner points of each wall surface within the target construction space. Then, it obtains the distance between each concave corner point and the working robot, determines the distance difference between the distances corresponding to two concave corner points located on at least one side, and finally controls the movement of the working robot based on these distance differences. This application, by identifying the concave corner points of each wall surface in the target construction space and determining the distance between each concave corner point and the working robot, controls the movement of the working robot based on these distances, ensuring the operating accuracy of the working robot. When applied to a spraying robot, this technical solution can achieve automatic or assisted drawing of squaring lines and improve the drawing accuracy of squaring lines.

[0021] Other features and advantages of the embodiments of this application will be described in detail in the following detailed description section. Attached Figure Description

[0022] The accompanying drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the following detailed description to explain the embodiments of this application, but do not constitute a limitation on the embodiments of this application. In the drawings:

[0023] Figure 1 The schematic diagram illustrates a flow chart of a control method for a work robot according to an embodiment of this application;

[0024] Figures 2(a) and 2(b) schematically illustrate a ground spraying operation process according to a specific embodiment of this application;

[0025] Figure 3 The illustration schematically shows the effect before point cloud clustering removal according to a specific embodiment of this application;

[0026] Figure 4 This illustration schematically shows the effect of point cloud clustering removal according to a specific embodiment of this application;

[0027] Figures 5(a), 5(b) and 5(c) schematically illustrate a process for adjusting the position and posture of a work robot according to a specific embodiment of this application;

[0028] Figure 6 A schematic block diagram of a computer device according to an embodiment of this application is shown. Detailed Implementation

[0029] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for illustration and explanation of the embodiments of this application and are not intended to limit the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0030] It should be noted that if the embodiments of this application involve directional indicators (such as up, down, left, right, front, back, etc.), the directional indicators are only used to explain the relative positional relationship and movement of the components in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indicators will also change accordingly.

[0031] Furthermore, if the embodiments of this application involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed in this application.

[0032] Figure 1 The illustration schematically shows a flowchart of a control method for a work robot according to an embodiment of this application. Figure 1 As shown, this application provides a control method for a work robot. The work robot includes a point cloud acquisition device and is located within a target construction space. Taking the application of this control method to a processor as an example, the control method may include the following steps:

[0033] Step S101: Obtain the initial point cloud of the target construction space collected by the point cloud acquisition device.

[0034] Step S102: Based on the initial point cloud, identify the concave corner points of each wall surface in the target construction space.

[0035] Step S103: Obtain the concave corner distance corresponding to each concave corner point. The concave corner distance corresponding to each concave corner point is the distance between the concave corner point and the working robot.

[0036] Step S104: Determine the distance difference between the concave corner points corresponding to two concave corner points located on at least one side.

[0037] Step S105: Control the movement of the work robot based on the distance difference.

[0038] The control method for a work robot provided in this application embodiment can be used to control the work robot. The work robot includes a point cloud acquisition device. The point cloud acquisition device can be a multi-line lidar or other device capable of acquiring point clouds. The target construction space refers to the construction space where the work robot performs its operations, and the target construction space contains multiple walls. Inside the target construction space, two adjacent walls can form a concave corner.

[0039] In this embodiment, the work robot is located within the target construction space. An initial point cloud of the target construction space can be acquired using a point cloud acquisition device. The processor can then obtain the initial point cloud acquired by the acquisition device and identify the concave corner points of each wall in the target construction space. After identifying the concave corner points, the processor can obtain the distance between each concave corner point, i.e., the distance between the concave corner point and the work robot. It is understood that the concave corner point distance can be determined by the processor based on the initial point cloud, or it can be obtained by using a distance acquisition device (e.g., a single-line lidar) installed on the work robot. Further, the processor can determine the distance difference between the concave corner distances corresponding to two concave corner points located on at least one side, and determine whether the distance difference is less than a preset distance difference. The preset distance difference can be determined according to the actual control accuracy requirements. If the distance difference is less than the preset distance difference, the processor can control the work robot to move in a direction perpendicular to the sides where the two concave corner points are located.

[0040] In some implementations, the work robot can be a spraying robot, and the processor can control the work robot to perform ground spraying operations while moving, thereby drawing a directional line. If the distance difference is greater than or equal to a preset distance difference, the processor controls the work robot to stop the ground spraying operation and controls the work robot to adjust its position and / or attitude to reduce the possibility of deviation in the drawn directional line due to the deviation of the work robot's movement path.

[0041] In other implementations, the robot can carry a laser level. The processor controls the robot to move based on the distance difference. When the distance difference is less than a preset distance difference, the laser level is activated, which allows the user to draw the square line along the laser line, thus playing a role in assisting in the drawing of the square line.

[0042] Of course, by designing the attachments or actuators mounted on the robot, the robot can be used for other functions, such as transporting goods, and the relevant functions can be specifically implemented based on the control methods provided in the embodiments of this application. Examples will not be given here. For simplicity, the following will mainly use a painting robot as an example to introduce the control methods used for the robot.

[0043] Figures 2(a) and 2(b) schematically illustrate a ground spraying operation process according to a specific embodiment of this application. As shown in Figures 2(a) and 2(b), in this specific embodiment, after the processor identifies concave corner points in the target construction space based on the initial point cloud, isosceles triangles can be drawn, that is, the distance between the working robot and two concave corner points located on at least one side can be determined, and then the distance difference between the distances corresponding to the two concave corner points can be determined. In this way, the working robot can be controlled according to the distance difference. During the control process, a certain error is allowed. If the distance difference is less than the preset distance difference, it is considered that the distance between the working robot and the two concave corner points located on the same side is equal, and the working robot can be controlled to perform ground spraying operations to draw horizontal and vertical squaring lines.

[0044] The aforementioned technical solution acquires an initial point cloud of the target construction space from a point cloud acquisition device. Based on this initial point cloud, it identifies the concave corner points of each wall surface within the target construction space. Then, it obtains the distance between each concave corner point and the working robot, determines the distance difference between the distances corresponding to two concave corner points located on at least one side, and finally controls the movement of the working robot based on these distance differences. This application, by identifying the concave corner points of each wall surface in the target construction space and determining the distance between each concave corner point and the working robot, controls the movement of the working robot based on these distances, ensuring the operating accuracy of the working robot. When applied to a spraying robot, this technical solution can achieve automatic or assisted drawing of squaring lines and improve the drawing accuracy of squaring lines.

[0045] In this embodiment of the application, identifying concave corner points of each wall surface in the target construction space based on an initial point cloud includes: obtaining the first direction coordinate value of each point cloud data in the initial point cloud in a first direction; obtaining the point cloud identifier corresponding to each point cloud data; determining adjacent point cloud data in the initial point cloud based on the point cloud identifier corresponding to each point cloud data; determining the coordinate value difference between the first direction coordinate values ​​corresponding to adjacent point cloud data; and determining the concave corner point based on the coordinate value difference, wherein the concave corner point is the point corresponding to the point cloud data whose point cloud identifier is the target point cloud identifier among the adjacent point cloud data whose corresponding coordinate value difference is greater than the preset coordinate value difference.

[0046] The processor can identify concave corner points of each wall surface in the target construction space based on the initial point cloud. Specifically, each point cloud data includes a first-direction coordinate value in a first direction, a second-direction coordinate value in a second direction, and a third-direction coordinate value in a third direction. The processor can decompose each point cloud data to obtain the first-direction coordinate values ​​of each point cloud data. It should be noted that before decomposing the point cloud data, data preprocessing can be performed, such as angle pass-through filtering, to remove noise points and outliers. Furthermore, if the point cloud acquisition device uses a multi-line LiDAR, the point cloud data acquired by the acquisition device can be compressed to reduce measurement errors. Specifically, the point cloud data acquired by each LiDAR beam is sorted in ascending order to determine the point cloud identifier corresponding to each point cloud data. Then, the point cloud data with the same point cloud identifier among all the point cloud data acquired by all LiDAR beams are identified, and the average of the coordinate values ​​corresponding to the point cloud data with the same point cloud identifier is used as the coordinate values ​​of the compressed point cloud data.

[0047] After completing the aforementioned point cloud data processing, the processor can acquire the point cloud identifiers corresponding to each point cloud data. It is understood that the point cloud identifiers corresponding to the point cloud data can be determined based on the scanning direction of the point cloud acquisition device, i.e., according to the order in which the point cloud data were acquired. Thus, based on the point cloud identifiers corresponding to each point cloud data, the processor can identify two adjacent point cloud data as adjacent point cloud data, and then determine the coordinate difference between the first direction coordinate values ​​corresponding to the adjacent point cloud data. When the coordinate difference between adjacent point cloud data is greater than a preset coordinate difference, the point corresponding to the point cloud data with the target point cloud identifier is identified as a concave corner point. The preset coordinate difference can be determined based on the actual operational scenario. The target point cloud identifier refers to either the larger or smaller point cloud identifier among the adjacent point cloud data; the specific point cloud identifier chosen can be set according to the operational situation. In this way, the processor can identify concave corner points in the target construction space, facilitating subsequent control of the robot based on the distance between each concave corner point.

[0048] In this embodiment of the application, obtaining the point cloud identifier corresponding to each point cloud data includes: clustering the point cloud data in the initial point cloud according to the first direction coordinate value to obtain multiple point cloud clusters; determining the average value of the first direction coordinate value corresponding to the point cloud data in each point cloud cluster; merging and clustering the multiple point cloud clusters according to the average value of the first direction coordinate value to obtain the wall point cloud corresponding to each wall; and obtaining the point cloud identifier corresponding to each point cloud data in each wall point cloud.

[0049] Specifically, before acquiring the point cloud identifiers corresponding to each point cloud data, the processor can cluster the point cloud data in the initial point cloud based on a preset clustering algorithm, thereby obtaining multiple point cloud clusters. In this process, the clustering algorithm can be the DENCLUE clustering algorithm, the DBSCAN clustering algorithm, or other algorithms capable of point cloud clustering. Subsequently, based on the first direction coordinate values ​​corresponding to the point cloud data contained in each point cloud cluster, the processor can determine the average value of the first direction coordinate values ​​corresponding to each point cloud cluster. Based on the average value of the first direction coordinate values, the processor can merge and cluster multiple point cloud clusters to obtain the wall point cloud corresponding to each wall surface, thus achieving the merging of point cloud data for the same wall surface.

[0050] In addition, before clustering, the processor can perform numerical filtering on the first direction coordinate values ​​to determine the first direction coordinate values ​​that need to be filtered out, and remove the point cloud data corresponding to the first direction coordinate values ​​that need to be filtered out as noise points.

[0051] and, Figure 3 The illustration shows the effect before point cloud clustering removal according to a specific embodiment of this application. Figure 4 The illustration schematically shows the effect of point cloud cluster removal according to a specific embodiment of this application. For example... Figure 3 and Figure 4 As shown, before merging multiple point cloud clusters, to improve the accuracy of subsequent concave corner point recognition, the processor can determine the number of point cloud data in each cluster. If the number of point cloud data in any cluster is less than a preset number, the cluster is removed and not merged. This removes point cloud data that might interfere with the subsequent concave corner point recognition process.

[0052] If, following the aforementioned steps, some point cloud clusters are removed based on the number of point cloud data in each cluster, then after obtaining the point clouds of each wall, the processor can complete the wall point clouds based on adaptive interpolation and the first-direction coordinate values ​​corresponding to each point cloud data. Specifically, since some point cloud data was removed in the aforementioned steps, the processor can update the point cloud identifiers corresponding to each point cloud data, and determine adjacent point cloud data based on the updated identifiers, thereby determining the coordinate difference of the first-direction coordinate values ​​corresponding to adjacent point cloud data. Subsequently, based on the difference interval where the coordinate difference lies, linear interpolation can be performed between the first-direction coordinate values ​​corresponding to adjacent point cloud data to obtain the complete wall point cloud. In one example, if the coordinate difference is in the first difference interval, p linear interpolations can be performed; if the coordinate difference is in the second difference interval, q linear interpolations can be performed. The maximum value in the first difference interval is less than the minimum value in the second difference interval, and p is less than q. In this way, linear interpolation can be performed based on the coordinate difference between the first direction coordinates of adjacent point cloud data, making the filled data more accurate.

[0053] In this embodiment, multiple point cloud clusters each have a corresponding cluster identifier, which is determined based on the number of point cloud data in the cluster. Multiple point cloud clusters are merged and clustered according to the average value of the first direction coordinates to obtain wall point clouds corresponding to each wall surface. This includes: determining adjacent point cloud clusters among the multiple point cloud clusters based on the cluster identifier; determining a first difference in the average value of the first direction coordinates corresponding to adjacent point cloud clusters; and merging and clustering the multiple point cloud clusters according to the first difference to obtain wall point clouds, where each wall point cloud is obtained by merging and clustering adjacent point cloud clusters whose first difference is less than a preset average difference.

[0054] After obtaining multiple point cloud clusters, the processor can merge and cluster these clusters based on the average value of the first direction coordinates, thereby obtaining the wall point clouds corresponding to each wall surface, achieving the merging of point cloud data for the same wall surface. Specifically, each point cloud cluster has a corresponding cluster identifier, which is determined by sorting the point cloud data in the cluster in descending order. Thus, the processor can determine adjacent point cloud clusters among the multiple clusters based on the cluster identifiers. Adjacent point cloud clusters refer to two point cloud clusters with adjacent cluster identifiers. Subsequently, the processor can determine the first difference between the average values ​​of the first direction coordinates corresponding to adjacent point cloud clusters based on the average value of the first direction coordinates corresponding to the adjacent point cloud clusters. When the first difference is less than a preset average difference, the adjacent point cloud clusters are merged. The preset average difference is set according to the actual situation. In this way, after completing the merging and clustering of multiple point cloud clusters, the processor can obtain the wall point clouds corresponding to each wall surface.

[0055] In addition, the processor can perform quantile numerical filtering on the point cloud data based on the first direction coordinate value corresponding to each point cloud data in the point cloud cluster, further filtering out noise points.

[0056] In this embodiment of the application, the work robot also includes multiple distance detection devices, and the control method further includes: acquiring multiple target distance parameters based on the multiple distance detection devices; and adjusting the position and / or posture of the work robot according to the multiple target distance parameters.

[0057] The processor can adjust the position and / or attitude of the robot to improve the efficiency of subsequent ground spraying operations. Specifically, the robot is equipped with multiple distance detection devices. These devices can be single-line LiDAR or other devices capable of detecting distance parameters. The processor can acquire multiple initial distance parameters detected by these devices. These initial distance parameters refer to the distance from the wall to the detection devices. After filtering these initial distance parameters, the processor obtains multiple target distance parameters. Based on these target distance parameters, the processor can adjust the robot's position and / or attitude.

[0058] In this embodiment of the application, obtaining multiple target distance parameters based on multiple distance detection devices includes: obtaining multiple initial distance parameters detected by multiple distance detection devices; in the case that there is an out-of-range distance parameter among the multiple initial distance parameters, determining the target side where the distance detection device corresponding to the out-of-range distance parameter is located, wherein the out-of-range distance parameter is an initial distance parameter that is greater than a preset distance parameter threshold; removing the initial distance parameters detected by the distance detection devices on the target side from the multiple initial distance parameters to obtain multiple target distance parameters.

[0059] Multiple distance detection devices are respectively installed on each side of the work robot to detect the initial distance parameters between the work robot and each wall. Each side has two or more distance detection devices. After the processor acquires multiple initial distance parameters detected by the multiple distance detection devices, it can filter these initial distance parameters to obtain multiple target distance parameters. Specifically, the processor can determine whether there are any out-of-range distance parameters among the multiple initial distance parameters, i.e., initial distance parameters greater than a preset distance parameter threshold. The preset distance parameter threshold can be determined based on the size of the target construction space. If there are out-of-range distance parameters among the multiple initial distance parameters, the processor can identify the distance detection device that detected the out-of-range distance parameter and further determine the target side where the distance detection device that detected the out-of-range distance parameter is located. Subsequently, the processor can remove the initial distance parameters detected by the distance detection devices on the target side from the multiple initial distance parameters to obtain multiple target distance parameters, thereby completing the filtering process of multiple initial distance parameters. For example, if there are out-of-range distance parameters among the multiple initial distance parameters, the target side where the distance detection device that detected the out-of-range distance parameter is located can be determined. Assuming there are three distance detection devices on the side of the target, the initial distance parameters detected by these three devices are removed, resulting in multiple target distance parameters. This removes invalid data, allowing us to focus only on the distances between the robot and the walls in the target construction space, thereby improving the accuracy of adjusting the robot's position and / or attitude.

[0060] In this embodiment, multiple distance detection devices are respectively disposed on each side of the work robot. The robot's posture is adjusted based on multiple target distance parameters, including: determining a second difference between two adjacent target distance parameters, wherein the two adjacent target distance parameters are detected by distance detection devices disposed on the same side; if the second difference is greater than a preset target distance parameter difference, controlling the work robot to rotate clockwise until the second difference is less than the preset target distance parameter difference error; if the second difference is less than the preset target distance parameter difference, controlling the work robot to rotate counterclockwise until the second difference is less than the preset target distance parameter difference error.

[0061] The processor can adjust the robot's posture based on multiple target distance parameters. Specifically, two or more distance detection devices are installed on each side. Therefore, based on the installation position of the distance detection devices, the processor can determine two adjacent target distance parameters from among the multiple target distance parameters. Specifically, it determines two target distance parameters d detected by distance detection devices located on the same side. i and d i+1 Let the distance parameters be the distances between two adjacent targets. The processor can then further determine a second difference between these two distance parameters. If the second difference is greater than a preset target distance parameter difference, the robot is controlled to rotate clockwise. If the second difference is less than the preset target distance parameter difference, the robot is controlled to rotate counter-clockwise. During rotation, the processor can update the second difference based on the real-time detected initial distance parameters and control the robot to stop rotating when the second difference is less than the preset target distance parameter difference error. Both the preset target distance parameter difference and the preset target distance parameter difference error can be determined according to actual control accuracy requirements. Furthermore, it should be noted that the rotation direction of the robot is not limited to the aforementioned directions and can be adjusted based on the installation position of the distance detection device and the difference between the minuend and subtrahend of the distances between two adjacent targets. This allows for adjustment of the robot's posture, ensuring the robot remains parallel to the wall and improving the efficiency of subsequent ground spraying operations.

[0062] In this embodiment, multiple distance detection devices are respectively disposed on each side of the work robot. The position of the work robot is adjusted according to multiple target distance parameters, including: acquiring a first distance parameter detected by a distance detection device disposed on a first side and a second distance parameter detected by a distance detection device disposed on a second side, wherein the first side and the second side are oppositely disposed and parallel to each other on the work robot, and the multiple target distance parameters include the first distance parameter and the second distance parameter; when the first distance parameter is greater than the second distance parameter, controlling the work robot to move towards the side where the distance detection device corresponding to the first distance parameter is located.

[0063] Before adjusting the position and / or posture of the robot, multiple initial distance parameters collected by various distance detection devices need to be filtered. If some initial distance parameters (i.e., those detected by the distance detection devices on the target side) have been removed, the processor cannot adjust the robot's position based solely on the initial distance parameters detected by the distance detection devices on the sides that are opposite and parallel to the target side. Therefore, if both the first distance parameter detected by the distance detection device on the first side and the second distance parameter detected by the distance detection device on the second side are included in the multiple target distance parameters, the processor can determine the larger value between the first and second distance parameters. If the first distance parameter is greater than the second distance parameter, the robot can be controlled to move towards the side where the distance detection device corresponding to the first distance parameter is located, until the third difference between the first and second distance parameters is less than a preset position adjustment threshold. Here, the first and second sides refer to the opposite and parallel sides of the robot, and the preset position adjustment threshold can be adjusted according to actual control accuracy requirements.

[0064] Alternatively, the average value of the first distance parameter can be determined based on the first distance parameter, and the average value of the second distance parameter can be determined based on the second distance parameter. Referring to the steps described above, when the average value of the first distance parameter is greater than the average value of the second distance parameter, the robot is controlled to move towards the side corresponding to the average value of the first distance parameter.

[0065] This allows for the adjustment of the robot's position, enabling it to move to the middle of two parallel walls, thus improving the imaging effect of the point cloud acquisition device and facilitating the acquisition of the initial point cloud of the target construction space.

[0066] Figures 5(a), 5(b), and 5(c) schematically illustrate a process for adjusting the position and posture of a work robot according to a specific embodiment of this application. Figure 5(a) shows the position and posture of the work robot before adjustment. Figure 5(b) shows the position and posture of the work robot during adjustment. Figure 5(c) shows the position and posture of the work robot after adjustment. As shown in Figures 5(a), 5(b), and 5(c), in a specific embodiment of this application, the position and posture of the work robot can be adjusted according to the aforementioned method of controlling the adjustment of the work robot's position and posture, enabling the work robot to accurately move to the middle position between the two walls. Thus, adjusting the position and posture of the work robot facilitates the subsequent acquisition of the initial point cloud of the target construction space by the point cloud acquisition device.

[0067] In this embodiment of the application, the control method further includes: obtaining the vertical distance between the working robot and each wall; determining whether any vertical distance is less than a preset anti-collision distance; and controlling the working robot to stop moving if any vertical distance is less than the preset anti-collision distance.

[0068] Specifically, based on the initial point cloud acquired by the point cloud acquisition device, or by installing a vertical distance detection device (such as ultrasonic radar) on the robot, the processor can obtain the vertical distance between the robot and each wall surface. Subsequently, the processor can determine whether any vertical distance is less than a preset anti-collision distance, and if any vertical distance is less than the preset anti-collision distance, control the robot to stop moving. The preset anti-collision distance can be set according to actual conditions. This reduces the possibility of the robot colliding with the walls during ground spraying operations.

[0069] Figure 6 A schematic block diagram of a computer device according to an embodiment of this application is shown. Figure 6 As shown in the figure, this application embodiment also provides a computer device, which includes a memory 610 and a processor 620. The memory 610 stores a computer program, and the processor 620 executes the computer program to implement the above-described control method for a work robot.

[0070] Specifically, in this embodiment, the processor 620 can be configured to: acquire an initial point cloud of the target construction space acquired by the point cloud acquisition device; identify concave corner points of each wall in the target construction space based on the initial point cloud; acquire the concave corner point distance corresponding to each concave corner point, wherein the concave corner point distance corresponding to the concave corner point is the distance between the concave corner point and the working robot; determine the distance difference between the concave corner point distances corresponding to two concave corner points located on at least one side; and control the working robot to move according to the distance difference.

[0071] In one embodiment, the processor 620 is further configured to: acquire the first direction coordinate values ​​of each point cloud data in the initial point cloud in a first direction; acquire the point cloud identifier corresponding to each point cloud data; determine adjacent point cloud data in the initial point cloud based on the point cloud identifier corresponding to each point cloud data; determine the coordinate value difference between the first direction coordinate values ​​corresponding to adjacent point cloud data; and determine a concave corner point based on the coordinate value difference, wherein the concave corner point is the point corresponding to the point cloud data whose coordinate value difference is greater than a preset coordinate value difference and whose point cloud identifier is the target point cloud identifier among the adjacent point cloud data.

[0072] In one embodiment, the processor 620 is further configured to: cluster the point cloud data in the initial point cloud according to the first direction coordinate value to obtain multiple point cloud clusters; determine the average value of the first direction coordinate value corresponding to the point cloud data in each point cloud cluster; merge and cluster the multiple point cloud clusters according to the average value of the first direction coordinate value to obtain the wall point cloud corresponding to each wall; and obtain the point cloud identifier corresponding to each point cloud data in each wall point cloud.

[0073] In one embodiment, the processor 620 is further configured to: determine adjacent point cloud clusters among multiple point cloud clusters based on cluster identifiers; determine a first difference between the average values ​​of the first direction coordinates corresponding to the adjacent point cloud clusters; and merge and cluster the multiple point cloud clusters based on the first difference to obtain each wall point cloud, wherein each wall point cloud is obtained by merging and clustering adjacent point cloud clusters whose corresponding first difference is less than the difference of the preset average value.

[0074] In one embodiment, the processor 620 is further configured to: acquire multiple target distance parameters based on multiple distance detection devices; and adjust the position and / or posture of the robot according to the multiple target distance parameters.

[0075] In one embodiment, the processor 620 is further configured to: determine a second difference between two adjacent target distance parameters among a plurality of target distance parameters, wherein the two adjacent target distance parameters are detected by a distance detection device disposed on the same side; if the second difference is greater than a preset target distance parameter difference, control the working robot to rotate clockwise until the second difference is less than the preset target distance parameter difference error; if the second difference is less than the preset target distance parameter difference, control the working robot to rotate counterclockwise until the second difference is less than the preset target distance parameter difference error.

[0076] In one embodiment, the processor 620 is further configured to: acquire a first distance parameter detected by a distance detection device located on a first side and a second distance parameter detected by a distance detection device located on a second side, wherein the first side and the second side are oppositely arranged and parallel to each other on the working robot, and the plurality of target distance parameters include the first distance parameter and the second distance parameter; and, if the first distance parameter is greater than the second distance parameter, control the working robot to move in the direction of the side where the distance detection device corresponding to the first distance parameter is located.

[0077] In one embodiment, the processor 620 is further configured to: acquire multiple initial distance parameters detected by multiple distance detection devices; if there is an out-of-range distance parameter among the multiple initial distance parameters, determine the target side where the distance detection device corresponding to the out-of-range distance parameter is located, wherein the out-of-range distance parameter is an initial distance parameter that is greater than a preset distance parameter threshold; and remove the initial distance parameters detected by the distance detection devices on the target side from the multiple initial distance parameters to obtain multiple target distance parameters.

[0078] In one embodiment, the processor 620 is further configured to: acquire the vertical distance between the robot and each wall; determine whether any vertical distance is less than a preset anti-collision distance; and control the robot to stop moving if any vertical distance is less than the preset anti-collision distance.

[0079] The aforementioned technical solution acquires an initial point cloud of the target construction space from a point cloud acquisition device. Based on this initial point cloud, it identifies the concave corner points of each wall surface within the target construction space. Then, it obtains the distance between each concave corner point and the working robot, determines the distance difference between the distances corresponding to two concave corner points located on at least one side, and finally controls the movement of the working robot based on these distance differences. This application, by identifying the concave corner points of each wall surface in the target construction space and determining the distance between each concave corner point and the working robot, controls the movement of the working robot based on these distances, ensuring the operating accuracy of the working robot. When applied to a spraying robot, this technical solution can achieve automatic or assisted drawing of squaring lines and improve the drawing accuracy of squaring lines.

[0080] This application also provides a work robot, including: a robot body; a point cloud acquisition device; and a processor.

[0081] This application also provides a machine-readable storage medium storing instructions that cause a machine to execute the above-described control method for a work robot.

[0082] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0083] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0084] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0085] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0086] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0087] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0088] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0089] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0090] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A control method for a work robot, characterized in that, The work robot includes a point cloud acquisition device, the work robot is located within the target construction space, the work robot is a spraying work robot, and the control method includes: Acquire the initial point cloud of the target construction space collected by the point cloud acquisition device; Based on the initial point cloud, the concave corner points of each wall surface in the target construction space are identified; Obtain the concave corner distance corresponding to each concave corner point, where the concave corner distance is the distance between the concave corner point and the working robot. Determine the distance difference between the distances between two concave corner points located on at least one side; The robot is controlled to move based on the distance difference. The step of controlling the movement of the work robot based on the distance difference includes: If the distance difference is less than the preset distance difference, the robot is controlled to move along the direction perpendicular to the two concave corners, while simultaneously performing ground spraying to automatically draw the directional lines. If the distance difference is greater than or equal to the preset distance difference, the robot is controlled to stop the ground spraying operation, and the position and / or posture of the robot are adjusted.

2. The control method according to claim 1, characterized in that, The step of identifying concave corner points of each wall surface in the target construction space based on the initial point cloud includes: Obtain the first-direction coordinate values ​​of each point cloud data in the initial point cloud in the first direction; Obtain the point cloud identifier corresponding to each of the aforementioned point cloud data; Based on the point cloud identifiers corresponding to each of the point cloud data, the adjacent point cloud data in the initial point cloud are determined; Determine the coordinate difference between the first direction coordinate values ​​corresponding to the adjacent point cloud data; The concave corner point is determined based on the coordinate value difference. The concave corner point is the point in the adjacent point cloud data whose coordinate value difference is greater than the preset coordinate value difference and whose point cloud identifier is the target point cloud identifier.

3. The control method according to claim 2, characterized in that, The acquisition of the point cloud identifier corresponding to each of the point cloud data includes: The point cloud data in the initial point cloud are clustered based on the first direction coordinate values ​​to obtain multiple point cloud clusters; Determine the average value of the first direction coordinates corresponding to the point cloud data in each of the point cloud clusters; Based on the average value of the first direction coordinates, the multiple point cloud clusters are merged and clustered to obtain the wall point cloud corresponding to each wall surface; Obtain the point cloud identifier corresponding to each point cloud data in the aforementioned wall point cloud.

4. The control method according to claim 3, characterized in that, Each of the multiple point cloud clusters has a corresponding cluster identifier, which is determined based on the number of point cloud data in the cluster. The step of merging and clustering the multiple point cloud clusters based on the average value of the first directional coordinates to obtain the wall point cloud corresponding to each wall surface includes: Based on the cluster identifier, determine the adjacent point cloud clusters among the plurality of point cloud clusters; Determine the first difference of the average value of the first directional coordinate values ​​corresponding to the adjacent point cloud clusters; The multiple point cloud clusters are merged and clustered according to the first difference to obtain each wall point cloud. Each wall point cloud is obtained by merging and clustering adjacent point cloud clusters whose first difference is less than the preset average difference.

5. The control method according to claim 1, characterized in that, The robot also includes multiple distance detection devices, and the control method further includes: Obtain multiple target distance parameters based on the multiple distance detection devices; The position and / or attitude of the robot are adjusted based on the multiple target distance parameters.

6. The control method according to claim 5, characterized in that, The plurality of distance detection devices are respectively disposed on each side of the working robot, and adjust the posture of the working robot according to the plurality of target distance parameters, including: Determine a second difference between two adjacent target distance parameters among the plurality of target distance parameters, wherein the two adjacent target distance parameters are detected by a distance detection device disposed on the same side; If the second difference is greater than the preset target distance parameter difference, the robot is controlled to rotate clockwise until the second difference is less than the preset target distance parameter difference error. If the second difference is less than the preset target distance parameter difference, the robot is controlled to rotate counterclockwise until the second difference is less than the preset target distance parameter difference error.

7. The control method according to claim 5, characterized in that, The plurality of distance detection devices are respectively disposed on each side of the working robot, and adjust the position of the working robot according to the plurality of target distance parameters, including: The system acquires a first distance parameter detected by a distance detection device located on a first side and a second distance parameter detected by a distance detection device located on a second side, wherein the first side and the second side are oppositely arranged and parallel to each other on the working robot, and the plurality of target distance parameters include the first distance parameter and the second distance parameter; If the first distance parameter is greater than the second distance parameter, the robot is controlled to move towards the side where the distance detection device corresponding to the first distance parameter is located.

8. The control method according to claim 5, characterized in that, The process of obtaining multiple target distance parameters based on the multiple distance detection devices includes: Obtain multiple initial distance parameters detected by the multiple distance detection devices; If there is an out-of-range distance parameter among the plurality of initial distance parameters, the target side where the distance detection device corresponding to the out-of-range distance parameter is located is determined, wherein the out-of-range distance parameter is an initial distance parameter that is greater than a preset distance parameter threshold; The initial distance parameters detected by the distance detection device on the side of the target are removed from the plurality of initial distance parameters to obtain a plurality of target distance parameters.

9. The control method according to claim 1, characterized in that, The control method further includes: The vertical distances between the robot and each of the walls are obtained respectively; Determine whether any of the stated vertical distances is less than a preset anti-collision distance; If any of the vertical distances is less than the preset anti-collision distance, the robot is controlled to stop moving.

10. A processor, characterized in that, It is configured to perform the control method for a work robot according to any one of claims 1 to 9.

11. A work robot, characterized in that, include: Robot body; Point cloud acquisition device; as well as The processor according to claim 10.

Images